Search code examples
pythonnumpybayesian

Iterate over integers in Bayesian Optimization package Python

I use Bayesian Optimization package (https://github.com/fmfn/BayesianOptimization) for parameter optimization. By default this library iterate over float points number but i neet iterate over integers, how can i perform that?

def black_box_function(x, y):
    return -x ** 2 - (y - 1) ** 2 + 1
from bayes_opt import BayesianOptimization
pbounds = {'x': (2, 4), 'y': (-3, 3)}

optimizer = BayesianOptimization(
    f=black_box_function,
    pbounds=pbounds,
    verbose=2, 
    random_state=1,
)

optimizer.maximize(
    init_points=2,
    n_iter=3,
)
# and as you can see it is iterated not over integers.
|   iter    |  target   |     x     |     y     |
-------------------------------------------------
|  1        | -7.135    |  2.834    |  1.322    |
|  2        | -7.78     |  2.0      | -1.186    |
|  3        | -19.0     |  4.0      |  3.0      |
|  4        | -16.3     |  2.378    | -2.413    |
|  5        | -4.441    |  2.105    | -0.005822 |
=================================================
Solution

  • You may read part 2 of the advanced tour for this.